Learning of correlated patterns in spin-glass networks by local learning rules
- 2 March 1987
- journal article
- research article
- Published by American Physical Society (APS) in Physical Review Letters
- Vol. 58 (9) , 949-952
- https://doi.org/10.1103/physrevlett.58.949
Abstract
Two simple storing prescriptions are presented for neural network models of N two-state neurons. These rules are local and allow the embedding of correlated patterns without errors in a network of spin-glass type. Starting from an arbitrary configuration of synaptic bonds, up to N patterns can be stored by successive modification of the synaptic efficacies. Proofs for the convergence are given. Extensions of these rules are possible.Keywords
This publication has 14 references indexed in Scilit:
- Associative recall of memory without errorsPhysical Review A, 1987
- Nonlinear Neural NetworksPhysical Review Letters, 1986
- A memory which forgetsJournal of Physics A: General Physics, 1986
- Networks of Formal Neurons and Memory PalimpsestsEurophysics Letters, 1986
- Storing Infinite Numbers of Patterns in a Spin-Glass Model of Neural NetworksPhysical Review Letters, 1985
- Learning and pattern recognition in spin glass modelsZeitschrift für Physik B Condensed Matter, 1985
- Collective properties of neural networks: A statistical physics approachBiological Cybernetics, 1984
- ‘Unlearning’ has a stabilizing effect in collective memoriesNature, 1983
- Neural networks and physical systems with emergent collective computational abilities.Proceedings of the National Academy of Sciences, 1982
- Analytic study of the memory storage capacity of a neural networkMathematical Biosciences, 1978